Try FastH3 (Text-to-Audio-Video) from Fastvideo →
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Image GenerationActive

openai / gpt-image-1-5

gpt-image-1-5

byopenai

Generate or edit images using text prompts or image edits with GPT Image 1.5. Supports multiple sizes, formats, and quality settings.

Text to ImageImage to ImageImage Editing
Model ID
gpt-image-1-5
Provider
openai
Updated
1776156990
wiro playground—openai/gpt-image-1-5
Reset to defaults

Required. Text description of the desired image or image edit. Maximum 32,000 characters.

Delete All
0 / 16
Maximum 16 image allowed

Optional. Image edit only. Input images to edit, up to 16.

Required. Output image size.

Sample outputs
Sample 1
Sample 2
Sample 3
Sample 4
Updated 1776156990

Overview

GPT Image 1.5 is an AI-powered tool designed for creating and editing images using natural language descriptions or by modifying existing images. It supports various image generation modes including text-to-image and image-to-image transformations.

What you can build

  • High-quality visual assets from descriptive text prompts
  • Image edits and enhancements using source images
  • Customized image outputs with control over size, quality, and format

Inputs

  • Prompt: Required text description for image generation or editing
  • Source Images (Edit): Optional input images for editing tasks (up to 16)
  • Mask Image (Edit): Optional mask to define editing regions
  • Size: Output image dimensions (auto, 1:1, 3:2, 2:3)
  • Quality: Output image quality level (low, medium, high)
  • Background: Transparency settings (auto, transparent, opaque)
  • Output Format: PNG, JPEG, or WEBP
  • Output Compression: JPEG or WEBP compression level (0-100)
  • Samples: Number of images to generate or edit (1-10)
  • Moderation Level: Content moderation level (auto, low)
  • Input Fidelity (Edit): Fidelity control for editing tasks (high, low)

Outputs

Generated or edited images with customizable parameters such as size, quality, background, and file format.

Recommended settings

For best results, use detailed prompts with specific lighting and style references. Select appropriate size and quality based on intended use. Adjust compression levels for optimal file size without sacrificing too much quality.

Limitations

  • Image editing requires compatible input images and masks
  • Output quality may vary depending on complexity of prompt
  • File size limitations apply to input images

Safety & compliance

This model is designed for generating creative visual content. Users must comply with applicable laws and regulations when using generated images. Content moderation helps filter inappropriate outputs.

Example prompts

Great starting points for gpt-image-1-5.

Seamlessly place this woman on a sunlit balcony overlooking Santorini, Greece with white buildings and blue domes in the background. Match the warm Mediterranean sunlight on her skin and clothes. Add natural soft shadows beneath her, slight wind movement in her hair, and a subtle sun glow on her shoulders. The background should have realistic depth of field with a slight blur on distant buildings. Maintain photorealistic lighting consistency throughout the entire scene.Image Generation
Place this watch on a dark slate surface with water droplets around it, dramatic side lighting, luxury product photography styleImage Generation
Replace only his clothing with a tailored navy blue suit, white dress shirt, red tie, and brown leather dress shoes. Do not alter his face, facial features, hair, skin tone, body shape, or pose in any way. Keep the exact same park background, lighting, and camera angle completely unchanged. Only modify the clothing.Image Generation
Transform this scene to winter with heavy snow covering the roof and yard, frost on the windows, and a warm glow from inside the houseImage Generation

API quick start

Run gpt-image-1-5 with a single API call.

POST https://api.wiro.ai/v1/Run/openai/gpt-image-1-5
{
  "prompt": "Seamlessly place this woman on a sunlit b…",
  "size": "auto",
  "quality": "low",
  "samples": 1
}
View full API docs